Generating Indicative-Informative Summaries with SumUM

tion. Our method was developed through the study of a corpus of abstracts written ssional abstractors. Relying on human judgment, we have evaluated indicativeness, informativeness, and text acceptability of the automatic summaries. The results thus far indicate good performance when compared with other summarization technologies.

• Type: Journal
• Year: 2002
• Where: COLING
• Authors: Horacio Saggion, Guy Lapalme
• Keywords: COLING 2002, COLING 2008, Human Judgment, Ssional Abstractors, Text Acceptability